Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5171 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1722. Min Act: -0.0001

Data Index: 172099 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1326. Min Act: -0.0001

Data Index: 123883 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1401. Min Act: -0.0001

Data Index: 576497 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1250. Min Act: -0.0002

Data Index: 644164 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1218. Min Act: -0.0002

Data Index: 738248 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1257. Min Act: -0.0001

Data Index: 1139456 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1281. Min Act: -0.0001

Data Index: 1289428 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1237. Min Act: -0.0001

Data Index: 1035077 (C4 (Web Text))

Max Activating Token Index: 230

Text #8

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1189. Min Act: -0.0001

Data Index: 547965 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1230. Min Act: -0.0001

Data Index: 534889 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1278. Min Act: -0.0001

Data Index: 1164581 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1212. Min Act: -0.0001

Data Index: 393156 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1214. Min Act: -0.0001

Data Index: 1353843 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1139. Min Act: -0.0001

Data Index: 1243751 (C4 (Web Text))

Max Activating Token Index: 766

Text #14

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1206. Min Act: -0.0001

Data Index: 816065 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1220. Min Act: -0.0001

Data Index: 52724 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1140. Min Act: -0.0001

Data Index: 335764 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1254. Min Act: -0.0001

Data Index: 124903 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1213. Min Act: -0.0001

Data Index: 1117278 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1136. Min Act: -0.0001

Data Index: 1335576 (C4 (Web Text))

Max Activating Token Index: 258